Hugging Face's logo

moos124
/
code-reasoning-0.5b

Transformers
Safetensors
Generated from Trainer
trl
hf_jobs
sft
Model card Files
xet
 Community
moos124 commited on
Commit
ff1cdc6
·
verified ·
1 Parent(s): 5d4cf4c

Training in progress, step 450, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +13 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c08b5c8d7c85c670fb281fe4b644b6295f19843e920cc077302bccc9f088568a
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:750f0e7efdc8e37a14ecc5bc5ba319218d5854f6081236b6ae8ca6c13a591984
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31907e44baa8b4eab7884611939f5a3ebbf0f45c970fca44fd0c93a214c8322e
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7f775348a1764a14d6f11b2a4a8a30e24aa7268352e03725d1b3af2aee6dc2b
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43eba60397466adac1442edb39b546391b90e1195ef90573e2cb80704a6826ad
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54172abd65c4b894245bc82a5e51893fc027b171b3b6cad3f63fcfe508d3884b
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3732f56883ef738ff880dd47a651c3b358007655dc2c409a69ddba472e4f20b1
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23db730c265d17bb98bdc34a288220c0f5ef2c3115f88a855e50ac6ec0ecab2c
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.09386666666666667,
6
  "eval_steps": 500,
7
- "global_step": 440,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -458,6 +458,16 @@
458
  "mean_token_accuracy": 0.726725485175848,
459
  "num_tokens": 2028837.0,
460
  "step": 440
 
 
 
 
 
 
 
 
 
 
461
  }
462
  ],
463
  "logging_steps": 10,
@@ -477,7 +487,7 @@
477
  "attributes": {}
478
  }
479
  },
480
- "total_flos": 9640671808588800.0,
481
  "train_batch_size": 4,
482
  "trial_name": null,
483
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.096,
6
  "eval_steps": 500,
7
+ "global_step": 450,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
458
  "mean_token_accuracy": 0.726725485175848,
459
  "num_tokens": 2028837.0,
460
  "step": 440
461
+ },
462
+ {
463
+ "entropy": 0.9712555348873139,
464
+ "epoch": 0.096,
465
+ "grad_norm": 0.3099062740802765,
466
+ "learning_rate": 9.993351448374873e-05,
467
+ "loss": 1.072590446472168,
468
+ "mean_token_accuracy": 0.7607480764389039,
469
+ "num_tokens": 2072441.0,
470
+ "step": 450
471
  }
472
  ],
473
  "logging_steps": 10,
 
487
  "attributes": {}
488
  }
489
  },
490
+ "total_flos": 9843312687547392.0,
491
  "train_batch_size": 4,
492
  "trial_name": null,
493
  "trial_params": null